© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 99254
    Prev
    Next
    INDEX
    Explanations

    "term" followed by "and"

    np_acts-logits-general · gemini-2.5-flash-lite

    "hello", "cat", "deliver"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iedz
    0.51
     برف
    0.49
    }}$,
    0.47
    <0xB3>
    0.46
     Bess
    0.46
    可能會
    0.46
     Bail
    0.46
    inée
    0.46
     sitting
    0.46
    empel
    0.46
    POSITIVE LOGITS
     Ciência
    0.48
     harmonize
    0.46
     কোর্স
    0.46
    Gloss
    0.43
     qualidade
    0.43
    ⁎
    0.42
    shiny
    0.42
    샨
    0.42
     ekonomi
    0.40
     तेरा
    0.40
    Activations Density 0.000%

    No Known Activations